Re: CPU hotplug: system hang on CPU hot remove during `pfmon --system-wide'

2007-06-06 Thread Gautham R Shenoy
On Tue, May 29, 2007 at 01:56:24PM -0700, Linus Torvalds wrote: > > > On Mon, 28 May 2007, Srivatsa Vaddagiri wrote: > > > > So is it settled now on what approach we are going to follow (freezer > > vs lock based) for cpu hotplug? I thought that Linus was not favouring > > freezer > > base

Re: CPU hotplug: system hang on CPU hot remove during `pfmon --system-wide'

2007-05-31 Thread Srivatsa Vaddagiri
On Wed, May 30, 2007 at 10:03:01AM -0700, Linus Torvalds wrote: > > and that's where all the problems started - sleepers needing to take that > > mutex > > recursively (which we did/do not support). > > > > foo() takes cpu_bitmask_lock and calls > > foo_bar() which also needs cpu_bitma

Re: CPU hotplug: system hang on CPU hot remove during `pfmon --system-wide'

2007-05-30 Thread Linus Torvalds
On Wed, 30 May 2007, Srivatsa Vaddagiri wrote: > > and that's where all the problems started - sleepers needing to take that > mutex > recursively (which we did/do not support). > > foo() takes cpu_bitmask_lock and calls > foo_bar() which also needs cpu_bitmask_lock > > What is

Re: CPU hotplug: system hang on CPU hot remove during `pfmon --system-wide'

2007-05-30 Thread Srivatsa Vaddagiri
On Tue, May 29, 2007 at 01:56:24PM -0700, Linus Torvalds wrote: > As far as I'm concerned, we should > - use "preempt_disable()" to protect against CPU's coming and going > - use "stop_machine()" or similar that already honors preemption, and >which I trust a whole lot more than freezer. >

Re: CPU hotplug: system hang on CPU hot remove during `pfmon --system-wide'

2007-05-29 Thread Rusty Russell
On Tue, 2007-05-29 at 13:56 -0700, Linus Torvalds wrote: > > On Mon, 28 May 2007, Srivatsa Vaddagiri wrote: > > > > So is it settled now on what approach we are going to follow (freezer > > vs lock based) for cpu hotplug? I thought that Linus was not favouring > > freezer > > based approach

Re: CPU hotplug: system hang on CPU hot remove during `pfmon --system-wide'

2007-05-29 Thread Linus Torvalds
On Mon, 28 May 2007, Srivatsa Vaddagiri wrote: > > So is it settled now on what approach we are going to follow (freezer > vs lock based) for cpu hotplug? I thought that Linus was not favouring > freezer > based approach sometime back .. As far as I'm concerned, we should - use "preemp

Re: CPU hotplug: system hang on CPU hot remove during `pfmon --system-wide'

2007-05-27 Thread Srivatsa Vaddagiri
On Mon, May 28, 2007 at 10:54:43AM +0900, Satoru Takeuchi wrote: > Since I'm investigating this problem now, I'm glad if someone > reports the test result on other arch or freezer. I suspect the freezer based approach will not have this problem. Gautham could probably verify that. Andrew/Linus,

CPU hotplug: system hang on CPU hot remove during `pfmon --system-wide'

2007-05-27 Thread Satoru Takeuchi
Hi, I found a bug on CPU hotplug. If `pfmon --system-wide' is running, CPU hot remove causes system hang. On the other hand, CPU hot add during that command seems to work fine. I detected this problem on my ia64 box, and I don't know that this problem is also occur on any arch or freezer based CP